Jie Liu

Chang Zhou, Jie Liu, Jie Tang et al.

Video Frame Interpolation (VFI) aims to synthesize non-existent intermediate frames between existent frames. Flow-based VFI algorithms estimate intermediate motion fields to warp the existent frames. Real-world motions' complexity and the reference frame's absence make motion estimation challenging. Many state-of-the-art approaches explicitly model the correlations between two neighboring frames for more accurate motion estimation. In common approaches, the receptive field of correlation modeling at higher resolution depends on the motion fields estimated beforehand. Such receptive field dependency makes common motion estimation approaches poor at coping with small and fast-moving objects. To better model correlations and to produce more accurate motion fields, we propose the Densely Queried Bilateral Correlation (DQBC) that gets rid of the receptive field dependency problem and thus is more friendly to small and fast-moving objects. The motion fields generated with the help of DQBC are further refined and up-sampled with context features. After the motion fields are fixed, a CNN-based SynthNet synthesizes the final interpolated frame. Experiments show that our approach enjoys higher accuracy and less inference time than the state-of-the-art. Source code is available at https://github.com/kinoud/DQBC.

Cilin Yan, Haochen Wang, Jie Liu et al.

Click-based interactive segmentation aims to generate target masks via human clicking, which facilitates efficient pixel-level annotation and image editing. In such a task, target ambiguity remains a problem hindering the accuracy and efficiency of segmentation. That is, in scenes with rich context, one click may correspond to multiple potential targets, while most previous interactive segmentors only generate a single mask and fail to deal with target ambiguity. In this paper, we propose a novel interactive segmentation network named PiClick, to yield all potentially reasonable masks and suggest the most plausible one for the user. Specifically, PiClick utilizes a Transformer-based architecture to generate all potential target masks by mutually interactive mask queries. Moreover, a Target Reasoning module(TRM) is designed in PiClick to automatically suggest the user-desired mask from all candidates, relieving target ambiguity and extra-human efforts. Extensive experiments on 9 interactive segmentation datasets demonstrate PiClick performs favorably against previous state-of-the-arts considering the segmentation results. Moreover, we show that PiClick effectively reduces human efforts in annotating and picking the desired masks. To ease the usage and inspire future research, we release the source code of PiClick together with a plug-and-play annotation tool at https://github.com/cilinyan/PiClick.

Jiacong Xu, Yi Zhang, Jiawei Peng et al.

Accurately estimating the 3D pose and shape is an essential step towards understanding animal behavior, and can potentially benefit many downstream applications, such as wildlife conservation. However, research in this area is held back by the lack of a comprehensive and diverse dataset with high-quality 3D pose and shape annotations. In this paper, we propose Animal3D, the first comprehensive dataset for mammal animal 3D pose and shape estimation. Animal3D consists of 3379 images collected from 40 mammal species, high-quality annotations of 26 keypoints, and importantly the pose and shape parameters of the SMAL model. All annotations were labeled and checked manually in a multi-stage process to ensure highest quality results. Based on the Animal3D dataset, we benchmark representative shape and pose estimation models at: (1) supervised learning from only the Animal3D data, (2) synthetic to real transfer from synthetically generated images, and (3) fine-tuning human pose and shape estimation models. Our experimental results demonstrate that predicting the 3D shape and pose of animals across species remains a very challenging task, despite significant advances in human pose estimation. Our results further demonstrate that synthetic pre-training is a viable strategy to boost the model performance. Overall, Animal3D opens new directions for facilitating future research in animal 3D pose and shape estimation, and is publicly available.

Yidong Cai, Jie Liu, Jie Tang et al.

Object modeling has become a core part of recent tracking frameworks. Current popular tackers use Transformer attention to extract the template feature separately or interactively with the search region. However, separate template learning lacks communication between the template and search regions, which brings difficulty in extracting discriminative target-oriented features. On the other hand, interactive template learning produces hybrid template features, which may introduce potential distractors to the template via the cluttered search regions. To enjoy the merits of both methods, we propose a robust object modeling framework for visual tracking (ROMTrack), which simultaneously models the inherent template and the hybrid template features. As a result, harmful distractors can be suppressed by combining the inherent features of target objects with search regions' guidance. Target-related features can also be extracted using the hybrid template, thus resulting in a more robust object modeling framework. To further enhance robustness, we present novel variation tokens to depict the ever-changing appearance of target objects. Variation tokens are adaptable to object deformation and appearance variations, which can boost overall performance with negligible computation. Experiments show that our ROMTrack sets a new state-of-the-art on multiple benchmarks.

Jie Liu, Mengting He, Xuequn Shang et al.

Graph anomaly detection (GAD) has gained increasing attention in recent years due to its critical application in a wide range of domains, such as social networks, financial risk management, and traffic analysis. Existing GAD methods can be categorized into node and edge anomaly detection models based on the type of graph objects being detected. However, these methods typically treat node and edge anomalies as separate tasks, overlooking their associations and frequent co-occurrences in real-world graphs. As a result, they fail to leverage the complementary information provided by node and edge anomalies for mutual detection. Additionally, state-of-the-art GAD methods, such as CoLA and SL-GAD, heavily rely on negative pair sampling in contrastive learning, which incurs high computational costs, hindering their scalability to large graphs. To address these limitations, we propose a novel unified graph anomaly detection framework based on bootstrapped self-supervised learning (named BOURNE). We extract a subgraph (graph view) centered on each target node as node context and transform it into a dual hypergraph (hypergraph view) as edge context. These views are encoded using graph and hypergraph neural networks to capture the representations of nodes, edges, and their associated contexts. By swapping the context embeddings between nodes and edges and measuring the agreement in the embedding space, we enable the mutual detection of node and edge anomalies. Furthermore, BOURNE can eliminate the need for negative sampling, thereby enhancing its efficiency in handling large graphs. Extensive experiments conducted on six benchmark datasets demonstrate the superior effectiveness and efficiency of BOURNE in detecting both node and edge anomalies.

Jie Liu, Mengting He, Guangtao Wang et al.

Imbalanced node classification widely exists in real-world networks where graph neural networks (GNNs) are usually highly inclined to majority classes and suffer from severe performance degradation on classifying minority class nodes. Various imbalanced node classification methods have been proposed recently which construct synthetic nodes and edges w.r.t. minority classes to balance the label and topology distribution. However, they are all based on the homophilic assumption that nodes of the same label tend to connect despite the wide existence of heterophilic edges in real-world graphs. Thus, they uniformly aggregate features from both homophilic and heterophilic neighbors and rely on feature similarity to generate synthetic edges, which cannot be applied to imbalanced graphs in high heterophily. To address this problem, we propose a novel GraphSANN for imbalanced node classification on both homophilic and heterophilic graphs. Firstly, we propose a unified feature mixer to generate synthetic nodes with both homophilic and heterophilic interpolation in a unified way. Next, by randomly sampling edges between synthetic nodes and existing nodes as candidate edges, we design an adaptive subgraph extractor to adaptively extract the contextual subgraphs of candidate edges with flexible ranges. Finally, we develop a multi-filter subgraph encoder that constructs different filter channels to discriminatively aggregate neighbor's information along the homophilic and heterophilic edges. Extensive experiments on eight datasets demonstrate the superiority of our model for imbalanced node classification on both homophilic and heterophilic graphs.

Zhifeng Ma, Hao Zhang, Jie Liu

Spatiotemporal predictive learning, which predicts future frames through historical prior knowledge with the aid of deep learning, is widely used in many fields. Previous work essentially improves the model performance by widening or deepening the network, but it also brings surging memory overhead, which seriously hinders the development and application of this technology. In order to improve the performance without increasing memory consumption, we focus on scale, which is another dimension to improve model performance but with low memory requirement. The effectiveness has been widely demonstrated in many CNN-based tasks such as image classification and semantic segmentation, but it has not been fully explored in recent RNN models. In this paper, learning from the benefit of multi-scale, we propose a general framework named Multi-Scale RNN (MS-RNN) to boost recent RNN models for spatiotemporal predictive learning. We verify the MS-RNN framework by thorough theoretical analyses and exhaustive experiments, where the theory focuses on memory reduction and performance improvement while the experiments employ eight RNN models (ConvLSTM, TrajGRU, PredRNN, PredRNN++, MIM, MotionRNN, PredRNN-V2, and PrecipLSTM) and four datasets (Moving MNIST, TaxiBJ, KTH, and Germany). The results show the efficiency that RNN models incorporating our framework have much lower memory cost but better performance than before. Our code is released at \url{https://github.com/mazhf/MS-RNN}.

Xinhai Chen, Jie Liu, Junjun Yan et al.

Mesh generation remains a key technology in many areas where numerical simulations are required. As numerical algorithms become more efficient and computers become more powerful, the percentage of time devoted to mesh generation becomes higher. In this paper, we present an improved structured mesh generation method. The method formulates the meshing problem as a global optimization problem related to a physics-informed neural network. The mesh is obtained by intelligently solving the physical boundary-constrained partial differential equations. To improve the prediction accuracy of the neural network, we also introduce a novel auxiliary line strategy and an efficient network model during meshing. The strategy first employs a priori auxiliary lines to provide ground truth data and then uses these data to construct a loss term to better constrain the convergence of the subsequent training. The experimental results indicate that the proposed method is effective and robust. It can accurately approximate the mapping (transformation) from the computational domain to the physical domain and enable fast high-quality structured mesh generation.

Wei Ji, Jingjing Li, Qi Bi et al.

Growing interests in RGB-D salient object detection (RGB-D SOD) have been witnessed in recent years, owing partly to the popularity of depth sensors and the rapid progress of deep learning techniques. Unfortunately, existing RGB-D SOD methods typically demand large quantity of training images being thoroughly annotated at pixel-level. The laborious and time-consuming manual annotation has become a real bottleneck in various practical scenarios. On the other hand, current unsupervised RGB-D SOD methods still heavily rely on handcrafted feature representations. This inspires us to propose in this paper a deep unsupervised RGB-D saliency detection approach, which requires no manual pixel-level annotation during training. It is realized by two key ingredients in our training pipeline. First, a depth-disentangled saliency update (DSU) framework is designed to automatically produce pseudo-labels with iterative follow-up refinements, which provides more trustworthy supervision signals for training the saliency network. Second, an attentive training strategy is introduced to tackle the issue of noisy pseudo-labels, by properly re-weighting to highlight the more reliable pseudo-labels. Extensive experiments demonstrate the superior efficiency and effectiveness of our approach in tackling the challenging unsupervised RGB-D SOD scenarios. Moreover, our approach can also be adapted to work in fully-supervised situation. Empirical studies show the incorporation of our approach gives rise to notably performance improvement in existing supervised RGB-D SOD models.

Peipei Liu, Hong Li, Zuoguang Wang et al.

Extracting cybersecurity entities such as attackers and vulnerabilities from unstructured network texts is an important part of security analysis. However, the sparsity of intelligence data resulted from the higher frequency variations and the randomness of cybersecurity entity names makes it difficult for current methods to perform well in extracting security-related concepts and entities. To this end, we propose a semantic augmentation method which incorporates different linguistic features to enrich the representation of input tokens to detect and classify the cybersecurity names over unstructured text. In particular, we encode and aggregate the constituent feature, morphological feature and part of speech feature for each input token to improve the robustness of the method. More than that, a token gets augmented semantic information from its most similar K words in cybersecurity domain corpus where an attentive module is leveraged to weigh differences of the words, and from contextual clues based on a large-scale general field corpus. We have conducted experiments on the cybersecurity datasets DNRTI and MalwareTextDB, and the results demonstrate the effectiveness of the proposed method.

Peipei Liu, Xin Zheng, Hong Li et al.

Modality representation learning is an important problem for multimodal sentiment analysis (MSA), since the highly distinguishable representations can contribute to improving the analysis effect. Previous works of MSA have usually focused on multimodal fusion strategies, and the deep study of modal representation learning was given less attention. Recently, contrastive learning has been confirmed effective at endowing the learned representation with stronger discriminate ability. Inspired by this, we explore the improvement approaches of modality representation with contrastive learning in this study. To this end, we devise a three-stages framework with multi-view contrastive learning to refine representations for the specific objectives. At the first stage, for the improvement of unimodal representations, we employ the supervised contrastive learning to pull samples within the same class together while the other samples are pushed apart. At the second stage, a self-supervised contrastive learning is designed for the improvement of the distilled unimodal representations after cross-modal interaction. At last, we leverage again the supervised contrastive learning to enhance the fused multimodal representation. After all the contrast trainings, we next achieve the classification task based on frozen representations. We conduct experiments on three open datasets, and results show the advance of our model.

Zhifeng Ma, Hao Zhang, Jie Liu

The drastic variation of motion in spatial and temporal dimensions makes the video prediction task extremely challenging. Existing RNN models obtain higher performance by deepening or widening the model. They obtain the multi-scale features of the video only by stacking layers, which is inefficient and brings unbearable training costs (such as memory, FLOPs, and training time). Different from them, this paper proposes a spatiotemporal multi-scale model called MS-LSTM wholly from a multi-scale perspective. On the basis of stacked layers, MS-LSTM incorporates two additional efficient multi-scale designs to fully capture spatiotemporal context information. Concretely, we employ LSTMs with mirrored pyramid structures to construct spatial multi-scale representations and LSTMs with different convolution kernels to construct temporal multi-scale representations. We theoretically analyze the training cost and performance of MS-LSTM and its components. Detailed comparison experiments with twelve baseline models on four video datasets show that MS-LSTM has better performance but lower training costs.

Jie Liu, Wenzhe Yin, Haochen Wang et al.

Few-shot point cloud segmentation seeks to generate per-point masks for previously unseen categories, using only a minimal set of annotated point clouds as reference. Existing prototype-based methods rely on support prototypes to guide the segmentation of query point clouds, but they encounter challenges when significant object variations exist between the support prototypes and query features. In this work, we present dynamic prototype adaptation (DPA), which explicitly learns task-specific prototypes for each query point cloud to tackle the object variation problem. DPA achieves the adaptation through prototype rectification, aligning vanilla prototypes from support with the query feature distribution, and prototype-to-query attention, extracting task-specific context from query point clouds. Furthermore, we introduce a prototype distillation regularization term, enabling knowledge transfer between early-stage prototypes and their deeper counterparts during adaption. By iteratively applying these adaptations, we generate task-specific prototypes for accurate mask predictions on query point clouds. Extensive experiments on two popular benchmarks show that DPA surpasses state-of-the-art methods by a significant margin, e.g., 7.43\% and 6.39\% under the 2-way 1-shot setting on S3DIS and ScanNet, respectively. Code is available at https://github.com/jliu4ai/DPA.

Jie Liu, Jiayi Shen, Pan Zhou et al.

Generalized Few-Shot Semantic Segmentation (GFSS) aims to extend a segmentation model to novel classes with only a few annotated examples while maintaining performance on base classes. Recently, pretrained vision-language models (VLMs) such as CLIP have been leveraged in GFSS to improve generalization on novel classes through multi-modal prototypes learning. However, existing prototype-based methods are inherently deterministic, limiting the adaptability of learned prototypes to diverse samples, particularly for novel classes with scarce annotations. To address this, we propose FewCLIP, a probabilistic prototype calibration framework over multi-modal prototypes from the pretrained CLIP, thus providing more adaptive prototype learning for GFSS. Specifically, FewCLIP first introduces a prototype calibration mechanism, which refines frozen textual prototypes with learnable visual calibration prototypes, leading to a more discriminative and adaptive representation. Furthermore, unlike deterministic prototype learning techniques, FewCLIP introduces distribution regularization over these calibration prototypes. This probabilistic formulation ensures structured and uncertainty-aware prototype learning, effectively mitigating overfitting to limited novel class data while enhancing generalization. Extensive experimental results on PASCAL-5$^i$ and COCO-20$^i$ datasets demonstrate that our proposed FewCLIP significantly outperforms state-of-the-art approaches across both GFSS and class-incremental setting. The code is available at https://github.com/jliu4ai/FewCLIP.

Hao Chen, Zhe-Ming Lu, Jie Liu

This paper focuses on proposing a deep learning-based monkey swing counting algorithm. Nowadays, there are very few papers on monkey detection, and even fewer papers on monkey swing counting. This research focuses on this gap and attempts to count the number of monkeys swinging their heads by deep learning. This paper further extends the traditional target detection algorithm. By analyzing the results of object detection, we localize the monkey's actions over a period of time. This paper analyzes the task of counting monkey head swings, and proposes the standard that accurately describes a monkey swinging its head. Under the guidance of this standard, the head-swing count in 50 monkey movement videos in this paper has achieved 94%.

Yanan Wu, Jie Liu, Xingyuan Bu et al.

This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs). Unlike traditional benchmarks that evaluate general mathematical reasoning with an average accuracy, ConceptMath systematically organizes math problems under a hierarchy of math concepts, so that mathematical reasoning can be evaluated at different granularity with concept-wise accuracies. Based on our ConcepthMath, we evaluate a broad range of LLMs, and we observe existing LLMs, though achieving high average accuracies on traditional benchmarks, exhibit significant performance variations across different math concepts and may even fail catastrophically on the most basic ones. Besides, we also introduce an efficient fine-tuning strategy to enhance the weaknesses of existing LLMs. Finally, we hope ConceptMath could guide the developers to understand the fine-grained mathematical abilities of their models and facilitate the growth of foundation models.

Wenxuan Wang, Zizhan Ma, Meidan Ding et al.

The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning, a cornerstone of clinical practice. This has catalyzed a shift from single-step answer generation to the development of LLMs explicitly designed for medical reasoning. This paper provides the first systematic review of this emerging field. We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies (e.g., supervised fine-tuning, reinforcement learning) and test-time mechanisms (e.g., prompt engineering, multi-agent systems). We analyze how these techniques are applied across different data modalities (text, image, code) and in key clinical applications such as diagnosis, education, and treatment planning. Furthermore, we survey the evolution of evaluation benchmarks from simple accuracy metrics to sophisticated assessments of reasoning quality and visual interpretability. Based on an analysis of 60 seminal studies from 2022-2025, we conclude by identifying critical challenges, including the faithfulness-plausibility gap and the need for native multimodal reasoning, and outlining future directions toward building efficient, robust, and sociotechnically responsible medical AI.

Hui Liu, Wenya Wang, Kecheng Chen et al.

In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories by composing known simpler concepts. However, existing vision-language models (VLMs), despite achieving significant progress through large-scale natural language supervision, often underperform in real-world applications because of sub-optimal prompt engineering and the inability to adapt effectively to target classes. To address these issues, we propose a Concept-guided Human-like Bayesian Reasoning (CHBR) framework. Grounded in Bayes' theorem, CHBR models the concept used in human image recognition as latent variables and formulates this task by summing across potential concepts, weighted by a prior distribution and a likelihood function. To tackle the intractable computation over an infinite concept space, we introduce an importance sampling algorithm that iteratively prompts large language models (LLMs) to generate discriminative concepts, emphasizing inter-class differences. We further propose three heuristic approaches involving Average Likelihood, Confidence Likelihood, and Test Time Augmentation (TTA) Likelihood, which dynamically refine the combination of concepts based on the test image. Extensive evaluations across fifteen datasets demonstrate that CHBR consistently outperforms existing state-of-the-art zero-shot generalization methods.

Hao Wang, Yu Bai, Guangmin Sun et al.

Powerful recognition algorithms are widely used in the Internet or important medical systems, which poses a serious threat to personal privacy. Although the law provides for diversity protection, e.g. The General Data Protection Regulation (GDPR) in Europe and Articles 1032 to 1039 of the civil code in China. However, as an important privacy disclosure event, biometric data is often hidden, which is difficult for the owner to detect and trace to the source. Human biometrics generally exist in images. In order to avoid the disclosure of personal privacy, we should prevent unauthorized recognition algorithms from acquiring the real features of the original image.

Shiqi Liu, Lu Wang, Jie Lian et al.

Relative radiometric normalization(RRN) of different satellite images of the same terrain is necessary for change detection, object classification/segmentation, and map-making tasks. However, traditional RRN models are not robust, disturbing by object change, and RRN models precisely considering object change can not robustly obtain the no-change set. This paper proposes auto robust relative radiometric normalization methods via latent change noise modeling. They utilize the prior knowledge that no change points possess small-scale noise under relative radiometric normalization and that change points possess large-scale radiometric noise after radiometric normalization, combining the stochastic expectation maximization method to quickly and robustly extract the no-change set to learn the relative radiometric normalization mapping functions. This makes our model theoretically grounded regarding the probabilistic theory and mathematics deduction. Specifically, when we select histogram matching as the relative radiometric normalization learning scheme integrating with the mixture of Gaussian noise(HM-RRN-MoG), the HM-RRN-MoG model achieves the best performance. Our model possesses the ability to robustly against clouds/fogs/changes. Our method naturally generates a robust evaluation indicator for RRN that is the no-change set root mean square error. We apply the HM-RRN-MoG model to the latter vegetation/water change detection task, which reduces the radiometric contrast and NDVI/NDWI differences on the no-change set, generates consistent and comparable results. We utilize the no-change set into the building change detection task, efficiently reducing the pseudo-change and boosting the precision.

Shaowei Chen, Yu Wang, Jie Liu et al.

Aspect sentiment triplet extraction (ASTE), which aims to identify aspects from review sentences along with their corresponding opinion expressions and sentiments, is an emerging task in fine-grained opinion mining. Since ASTE consists of multiple subtasks, including opinion entity extraction, relation detection, and sentiment classification, it is critical and challenging to appropriately capture and utilize the associations among them. In this paper, we transform ASTE task into a multi-turn machine reading comprehension (MTMRC) task and propose a bidirectional MRC (BMRC) framework to address this challenge. Specifically, we devise three types of queries, including non-restrictive extraction queries, restrictive extraction queries and sentiment classification queries, to build the associations among different subtasks. Furthermore, considering that an aspect sentiment triplet can derive from either an aspect or an opinion expression, we design a bidirectional MRC structure. One direction sequentially recognizes aspects, opinion expressions, and sentiments to obtain triplets, while the other direction identifies opinion expressions first, then aspects, and at last sentiments. By making the two directions complement each other, our framework can identify triplets more comprehensively. To verify the effectiveness of our approach, we conduct extensive experiments on four benchmark datasets. The experimental results demonstrate that BMRC achieves state-of-the-art performances.

Junyang Lin, Rui Men, An Yang et al.

In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1.9TB images and 292GB texts that cover a wide range of domains. We propose a cross-modal pretraining method called M6, referring to Multi-Modality to Multi-Modality Multitask Mega-transformer, for unified pretraining on the data of single modality and multiple modalities. We scale the model size up to 10 billion and 100 billion parameters, and build the largest pretrained model in Chinese. We apply the model to a series of downstream applications, and demonstrate its outstanding performance in comparison with strong baselines. Furthermore, we specifically design a downstream task of text-guided image generation, and show that the finetuned M6 can create high-quality images with high resolution and abundant details.

Ling Wang, Cheng Zhang, Zejian Luo et al.

Nowadays, Deep Learning as a service can be deployed in Internet of Things (IoT) to provide smart services and sensor data processing. However, recent research has revealed that some Deep Neural Networks (DNN) can be easily misled by adding relatively small but adversarial perturbations to the input (e.g., pixel mutation in input images). One challenge in defending DNN against these attacks is to efficiently identifying and filtering out the adversarial pixels. The state-of-the-art defense strategies with good robustness often require additional model training for specific attacks. To reduce the computational cost without loss of generality, we present a defense strategy called a progressive defense against adversarial attacks (PDAAA) for efficiently and effectively filtering out the adversarial pixel mutations, which could mislead the neural network towards erroneous outputs, without a-priori knowledge about the attack type. We evaluated our progressive defense strategy against various attack methods on two well-known datasets. The result shows it outperforms the state-of-the-art while reducing the cost of model training by 50% on average.

Zhongxu Hu, Yang Xing, Chen Lv et al.

Head pose estimation is a crucial problem for many tasks, such as driver attention, fatigue detection, and human behaviour analysis. It is well known that neural networks are better at handling classification problems than regression problems. It is an extremely nonlinear process to let the network output the angle value directly for optimization learning, and the weight constraint of the loss function will be relatively weak. This paper proposes a novel Bernoulli heatmap for head pose estimation from a single RGB image. Our method can achieve the positioning of the head area while estimating the angles of the head. The Bernoulli heatmap makes it possible to construct fully convolutional neural networks without fully connected layers and provides a new idea for the output form of head pose estimation. A deep convolutional neural network (CNN) structure with multiscale representations is adopted to maintain high-resolution information and low-resolution information in parallel. This kind of structure can maintain rich, high-resolution representations. In addition, channelwise fusion is adopted to make the fusion weights learnable instead of simple addition with equal weights. As a result, the estimation is spatially more precise and potentially more accurate. The effectiveness of the proposed method is empirically demonstrated by comparing it with other state-of-the-art methods on public datasets.

Junyang Lin, An Yang, Yichang Zhang et al.

Multi-modal pretraining for learning high-level multi-modal representation is a further step towards deep learning and artificial intelligence. In this work, we propose a novel model, namely InterBERT (BERT for Interaction), which is the first model of our series of multimodal pretraining methods M6 (MultiModality-to-MultiModality Multitask Mega-transformer). The model owns strong capability of modeling interaction between the information flows of different modalities. The single-stream interaction module is capable of effectively processing information of multiple modalilties, and the two-stream module on top preserves the independence of each modality to avoid performance downgrade in single-modal tasks. We pretrain the model with three pretraining tasks, including masked segment modeling (MSM), masked region modeling (MRM) and image-text matching (ITM); and finetune the model on a series of vision-and-language downstream tasks. Experimental results demonstrate that InterBERT outperforms a series of strong baselines, including the most recent multi-modal pretraining methods, and the analysis shows that MSM and MRM are effective for pretraining and our method can achieve performances comparable to BERT in single-modal tasks. Besides, we propose a large-scale dataset for multi-modal pretraining in Chinese, and we develop the Chinese InterBERT which is the first Chinese multi-modal pretrained model. We pretrain the Chinese InterBERT on our proposed dataset of 3.1M image-text pairs from the mobile Taobao, the largest Chinese e-commerce platform. We finetune the model for text-based image retrieval, and recently we deployed the model online for topic-based recommendation.

Qian Liu, Tao Wang, Jie Liu et al.

With the rapid development of digital multimedia, video understanding has become an important field. For action recognition, temporal dimension plays an important role, and this is quite different from image recognition. In order to learn powerful feature of videos, we propose a Collaborative Temporal Modeling (CTM) block (Figure 1) to learn temporal information for action recognition. Besides a parameter-free identity shortcut, as a separate temporal modeling block, CTM includes two collaborative paths: a spatial-aware temporal modeling path, which we propose the Temporal-Channel Convolution Module (TCCM) with unshared parameters for each spatial position (H*W) to build, and a spatial-unaware temporal modeling path. CTM blocks can seamlessly be inserted into many popular networks to generate CTM Networks and bring the capability of learning temporal information to 2D CNN backbone networks, which only capture spatial information. Experiments on several popular action recognition datasets demonstrate that CTM blocks bring the performance improvements on 2D CNN baselines, and our method achieves the competitive results against the state-of-the-art methods. Code will be made publicly available.

Qian Liu, Dongyang Cai, Jie Liu et al.

In this report, the method for the iqiyi submission to the task of ActivityNet 2019 Kinetics-700 challenge is described. Three models are involved in the model ensemble stage: TSN, HG-NL and StNet. We propose the hierarchical group-wise non-local (HG-NL) module for frame-level features aggregation for video classification. The standard non-local (NL) module is effective in aggregating frame-level features on the task of video classification but presents low parameters efficiency and high computational cost. The HG-NL method involves a hierarchical group-wise structure and generates multiple attention maps to enhance performance. Basing on this hierarchical group-wise structure, the proposed method has competitive accuracy, fewer parameters and smaller computational cost than the standard NL. For the task of ActivityNet 2019 Kinetics-700 challenge, after model ensemble, we finally obtain an averaged top-1 and top-5 error percentage 28.444% on the test set.

Jie Liu, Jiawen Liu, Wan Du et al.

Training deep learning models on mobile devices recently becomes possible, because of increasing computation power on mobile hardware and the advantages of enabling high user experiences. Most of the existing work on machine learning at mobile devices is focused on the inference of deep learning models (particularly convolutional neural network and recurrent neural network), but not training. The performance characterization of training deep learning models on mobile devices is largely unexplored, although understanding the performance characterization is critical for designing and implementing deep learning models on mobile devices. In this paper, we perform a variety of experiments on a representative mobile device (the NVIDIA TX2) to study the performance of training deep learning models. We introduce a benchmark suite and tools to study performance of training deep learning models on mobile devices, from the perspectives of memory consumption, hardware utilization, and power consumption. The tools can correlate performance results with fine-grained operations in deep learning models, providing capabilities to capture performance variance and problems at a fine granularity. We reveal interesting performance problems and opportunities, including under-utilization of heterogeneous hardware, large energy consumption of the memory, and high predictability of workload characterization. Based on the performance analysis, we suggest interesting research directions.

Yunpeng Li, Jie Liu, Yong Deng

In this paper, we present an illustration to the history of Artificial Intelligence(AI) with a statistical analysis of publish since 1940. We collected and mined through the IEEE publish data base to analysis the geological and chronological variance of the activeness of research in AI. The connections between different institutes are showed. The result shows that the leading community of AI research are mainly in the USA, China, the Europe and Japan. The key institutes, authors and the research hotspots are revealed. It is found that the research institutes in the fields like Data Mining, Computer Vision, Pattern Recognition and some other fields of Machine Learning are quite consistent, implying a strong interaction between the community of each field. It is also showed that the research of Electronic Engineering and Industrial or Commercial applications are very active in California. Japan is also publishing a lot of papers in robotics. Due to the limitation of data source, the result might be overly influenced by the number of published articles, which is to our best improved by applying network keynode analysis on the research community instead of merely count the number of publish.